Changelog and version bump.

CHANGELOG.md

@@ -247,3 +247,11 @@ Deprecated:
  - Kepler binaries (GTX 700s and Tesla K40/K80) are not longer provided via pip and need to be compiled from source. Kepler support might be fully removed in the future.
 
 
+### 0.40.0
+
+Features:
+ - Added 4-bit inference kernels for batch size=1. Currently support are the NF4, FP4 data types.
+ - Added support for quantizations of bfloat16 input data.
+
+Bug fixes:
+ - Added `device` variable for bitsandbytes layers to be compatible with PyTorch layers.

setup.py

@@ -18,7 +18,7 @@ def read(fname):
 
 setup(
     name=f"bitsandbytes",
-    version=f"0.39.1",
+    version=f"0.40.0",
     author="Tim Dettmers",
     author_email="dettmers@cs.washington.edu",
     description="k-bit optimizers and matrix multiplication routines.",